Commit Graph

28 Commits

Author SHA1 Message Date
reed
e8f3062a36 switch surface to sk_sp
BUG=skia:
GOLD_TRYBOT_URL= https://gold.skia.org/search2?unt=true&query=source_type%3Dgm&master=false&issue=1817383002
CQ_EXTRA_TRYBOTS=client.skia.compile:Build-Ubuntu-GCC-x86_64-Release-CMake-Trybot,Build-Mac-Clang-x86_64-Release-CMake-Trybot

Review URL: https://codereview.chromium.org/1817383002
2016-03-23 18:59:25 -07:00
reed
9ce9d6772d update callsites for Make image factories
not forced yet, as we still have the build-guard. waiting on chrome CL

BUG=skia:
GOLD_TRYBOT_URL= https://gold.skia.org/search2?unt=true&query=source_type%3Dgm&master=false&issue=1810813003

TBR=

Review URL: https://codereview.chromium.org/1810813003
2016-03-17 10:51:11 -07:00
cdalton
31c45bbd5a Fix nanobench SKP flushes between loops
Updates SKPBench to actually flush between draw loops, as this was the
original intent of the flush logic.

BUG=skia:
GOLD_TRYBOT_URL= https://gold.skia.org/search2?unt=true&query=source_type%3Dgm&master=false&issue=1715873002

Review URL: https://codereview.chromium.org/1715873002
2016-02-22 08:08:25 -08:00
joshualitt
dc5685ac37 Wire up resource cache stats dumping in nanobench
TBR=bsalomon@google.com
BUG=skia:

Review URL: https://codereview.chromium.org/1495543003
2015-12-02 14:08:25 -08:00
joshualitt
8fd844f38e reset shader compilations for stats
BUG=skia:

Review URL: https://codereview.chromium.org/1491823003
2015-12-02 13:36:47 -08:00
joshualitt
e45c81c8f3 Began logging more gpu stats from nanobench
BUG=skia:

Review URL: https://codereview.chromium.org/1489033004
2015-12-02 09:05:38 -08:00
cdalton
e6d2024c68 Flush GrContext between benchmark draw loops
This change updates a small subset of benchmarks to flush the GrContext
between draw loops (specifically SKP benchmarks, SampleApp, and the
warmup in visualbench). This helps improve timing accuracy by not
allowing the gpu to batch across draw boundaries in the affected
benchmarks.

BUG=skia:

Review URL: https://codereview.chromium.org/1427533002
2015-10-26 13:45:29 -07:00
mtklein
a1ebeb25e9 Remove const from const int loops.
This drives me nuts, and prevents `while (loops --> 0)`.

BUG=skia:

Review URL: https://codereview.chromium.org/1379923005
2015-10-01 09:43:39 -07:00
halcanary
96fcdcc219 Style Change: NULL->nullptr
DOCS_PREVIEW= https://skia.org/?cl=1316233002

Review URL: https://codereview.chromium.org/1316233002
2015-08-27 07:41:16 -07:00
cdalton
b4022965a2 Add loopSKP flag to nanobench
Adds a loopSKP flag that forces SKPBenches to draw with only 1 loop.

BUG=skia:

Review URL: https://codereview.chromium.org/1203193002
2015-06-25 10:51:56 -07:00
mtklein
bf9e600069 nanobench: split CPU and GPU .SKP tile sizes.
Let's make CPU-bound .SKP benching mimic Chrome's tiles.
Unfortunately, the CPU code also performs a lot better with those big wide tiles...

BUG=skia:

Review URL: https://codereview.chromium.org/1189863002
2015-06-16 10:41:27 -07:00
joshualitt
261c3ad7fd Change to add zoom animations to nanobench
BUG=skia:

Review URL: https://codereview.chromium.org/1061323003
2015-04-27 09:16:57 -07:00
robertphillips
1d24b8dfe9 Add matrix constructing helpers to SkMatrix
Review URL: https://codereview.chromium.org/1034273002
2015-03-26 19:57:08 -07:00
egdaniel
9a0f629973 Only use 256x256 tiles on hd2000 nanobench bots
Initial experiments did show that the 256 tile size fixed the hd2000 win7
nanobot failures. However it did not have any effect on other bots, so this
change is to move back to the larger tile size on all bots expect for the
hd2000.

BUG=skia:

Review URL: https://codereview.chromium.org/1022083002
2015-03-20 07:03:52 -07:00
egdaniel
5d09568a0c Move skp nanobench tile size back to 256x256 to see if it fixes nanobench crashes
Going back to old nanobench tile size to see if the increase to tile is what has been
causing recent nanobench crashes. The crashes seem very nondeterministic and hard to
debug manually.

256x256 is too small of a tile to give accurate gpu results but if this fixes we can try some compromise in the middle

BUG=skia:

Review URL: https://codereview.chromium.org/1022823003
2015-03-19 11:00:09 -07:00
bsalomon
cc4d6673a9 Increase default tile sizes in nanobench
R=mtklein@google.com

Review URL: https://codereview.chromium.org/982863003
2015-03-05 13:42:27 -08:00
tfarina
0004e7db42 Update references to skiaperf.com.
The new server is being run in perf.skia.org.

BUG=None
R=jcgregorio@google.com

Review URL: https://codereview.chromium.org/866943003
2015-01-26 06:47:55 -08:00
robertphillips
a3e52724ac Switch non-MPD nanobench path to use a separate canvas per tile
It is desirable that, when layer hoisting is disabled, the MPD and non-MPD timings be
roughly the same. Unfortunately, using a separate canvas for each tile (a requirement
for MPD) introduces its own discrepancy into the timing. Using a separate canvas for
each tile doesn't seem to make a difference for 8888 (see the non-MPD 8888 column below)
but slows down GPU rendering (see the non-MPD GPU column below). Since this is how
Chromium renders I propose switching to this regimen (even though it is "slowing down"
GPU rendering).

nanobench mean times (ms) with layer hoisting disabled (for desk_amazon.skp)

8888
                          MPD     non-MPD
1 canvas (old-style)     0.628    1.71
separate (new-style)     0.795    1.63

GPU
                          MPD     non-MPD
1 canvas (old-style)     2.34     1.69
separate (new-style)     2.32     2.66

Review URL: https://codereview.chromium.org/779643002
2014-12-09 10:27:54 -08:00
robertphillips
63242d7d24 Fix SKPBench tiling so MPD and non-MPD match
Two issues with the SKPBench tile computation were causing the MPD path to do more work:

The clip from the parent canvas wasn't being used to trim content off the edges of the MPD tiles

The non-MPD path was not taking the scale into account in its tile placement (resulting in it having fewer, larger active tiles when scaling).

Review URL: https://codereview.chromium.org/776273002
2014-12-04 08:31:03 -08:00
robertphillips
186a08ed72 Fix memory leak in nanobench
This is cleanup for (Add MultiPictureDraw to nanobench - https://codereview.chromium.org/731973005/)

Review URL: https://codereview.chromium.org/730343003
2014-11-21 06:53:00 -08:00
robertphillips
5b69377507 Add MultiPictureDraw to nanobench
I would like some guard against performance regressions on our side before turning layer hoisting on in Chromium.

TBR=bsalomon@google.com

Committed: https://skia.googlesource.com/skia/+/0ddad31012dabfc1267effc8071d37f7d606efbe

Review URL: https://codereview.chromium.org/731973005
2014-11-21 06:19:36 -08:00
robertphillips
e77dadd91a Revert of Add MultiPictureDraw to nanobench (patchset #7 id:120001 of https://codereview.chromium.org/731973005/)
Reason for revert:
Needs more work

Original issue's description:
> Add MultiPictureDraw to nanobench
>
> I would like some guard against performance regressions on our side before turning layer hoisting on in Chromium.
>
> TBR=bsalomon@google.com
>
> Committed: https://skia.googlesource.com/skia/+/0ddad31012dabfc1267effc8071d37f7d606efbe

TBR=mtklein@google.com,bsalomon@google.com
NOTREECHECKS=true
NOTRY=true

Review URL: https://codereview.chromium.org/750583002
2014-11-21 05:50:21 -08:00
robertphillips
0ddad31012 Add MultiPictureDraw to nanobench
I would like some guard against performance regressions on our side before turning layer hoisting on in Chromium.

TBR=bsalomon@google.com

Review URL: https://codereview.chromium.org/731973005
2014-11-21 05:35:54 -08:00
mtklein
6838d854a8 Try out SkTree in nanobench.
Looks like a fairly large recording speed win with no playback cost.

BUG=skia:

Review URL: https://codereview.chromium.org/653023003
2014-10-29 14:15:10 -07:00
mtklein
c7f7f467df Draw SKPs in 256x256 tiles in nanobench.
(This CL will certainly trigger performance regression alerts.  Tiled drawing is slower than non-tiled drawing.)

BUG=skia:

Review URL: https://codereview.chromium.org/669983002
2014-10-21 12:29:25 -07:00
mtklein
962890568d Distinguish common and unique names for skiaperf.com.
Turns out we tack on the size post-facto in ResultsWriter::bench(), so the only
place we need getUniqueName() to differ from getName() is SKPBench.

BUG=skia:
R=jcgregorio@google.com, mtklein@google.com

Author: mtklein@chromium.org

Review URL: https://codereview.chromium.org/552303004
2014-09-10 12:05:59 -07:00
robertphillips
c5ba71d2e5 Change SkPicture::draw to playback
R=reed@google.com

Author: robertphillips@google.com

Review URL: https://codereview.chromium.org/540963002
2014-09-04 08:42:50 -07:00
mtklein
92007583e4 SKPs-as-benches in nanobench
This is meant to replace bench_pictures.

CQ_EXTRA_TRYBOTS=tryserver.skia:Build-Mac10.7-Clang-Arm7-Release-iOS-Trybot

BUG=skia:
R=bsalomon@google.com, jcgregorio@google.com, mtklein@google.com

Author: mtklein@chromium.org

Review URL: https://codereview.chromium.org/425393004
2014-08-01 07:46:53 -07:00